A survey that organizes machine unlearning verification methods into behavioral and parametric categories and outlines open problems.
Box-Free Model Watermarks Are Prone to Black-Box Removal Attacks,
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
years
2025 2verdicts
UNVERDICTED 2roles
background 1polarities
background 1representative citing papers
GCP detects malicious agents in collaborative perception using spatial-temporal aware methods with a confidence-scaled loss and historical BEV flow reconstruction, achieving up to 34.69% AP@0.5 gains under a new BAC attack.
citing papers explorer
-
Towards Reliable Forgetting: A Survey on Machine Unlearning Verification
A survey that organizes machine unlearning verification methods into behavioral and parametric categories and outlines open problems.
-
GCP: Guarded Collaborative Perception with Spatial-Temporal Aware Malicious Agent Detection
GCP detects malicious agents in collaborative perception using spatial-temporal aware methods with a confidence-scaled loss and historical BEV flow reconstruction, achieving up to 34.69% AP@0.5 gains under a new BAC attack.